Obsidian Mind is an Obsidian vault that stores notes, links, indexes, and other accumulated context so AI coding agents can retain memory across sessions. It is designed for Claude Code and also supports Codex CLI and Gemini CLI through shared hooks, commands, and vault data. Its catalogue add-ons package the vault’s commands, agents, skills, hooks, instructions, settings, plugin, and MCP integration.
Borrowing it
Nothing to install: this file belongs to breferrari/obsidian-mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/commands/om-review-peer.mdgit clone --depth 1 https://github.com/breferrari/obsidian-mindWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/breferrari/obsidian-mind/om-review-peer)<a href="https://agentmods.dev/commands/breferrari/obsidian-mind/om-review-peer"><img src="https://agentmods.dev/badge/commands/breferrari/obsidian-mind/om-review-peer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/breferrari/obsidian-mind/om-review-peer"><img src="https://agentmods.dev/badge/commands/breferrari/obsidian-mind/om-review-peer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01019 |
| Opus 5 | $0.00000 | $0.00509 |
| Sonnet 5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
om-review-peer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Peer Review Writer
Write a peer review for a colleague on your company's review tool. Produces project feedback, principles, and performance summary — all within 1000-char limits, fact-checked against vault evidence.
Usage
/om-review-peer <Name>
Context: Review System
Adapt to your company's review system. Common patterns:
- Peers give comments only — typically no scores. Manager gives scores.
- Calibration may happen at a broader organizational level.
- Common review fields: per-project feedback, principles, Strengths, Areas of Development, Confidential Comment (manager-only). Check your tool's character limits.
Workflow
1. Gather Evidence
Load in order:
- Person note from
org/people/<Name>.md - PR evidence from
perf/evidence/<Name> PRs - <cycle>.md(run/om-peer-scanif missing) - Peer review notes from
work/active/(any active review writing notes) - Any brag sheet or impact overview the person shared (user provides)
- Relevant work notes (search vault for their name)
- Slack context if available
2. Assess Visibility
For each submitted project, classify your evidence level:
- Direct: Worked together daily, first-hand observations
- Reviewed: Saw their PRs, reviewed some code, aware of the work
- Informed: From their brag sheet or shared documents, limited personal observation
Be explicit about this in the review text. Never overclaim visibility.
3. Draft
For each section, draft within your tool's character limit. Use node --experimental-strip-types .claude/scripts/charcount.ts <file> "<section>" "" <limit> to verify.
Project feedback (per project):
- Lead with your relationship to the work ("worked alongside daily" vs "less direct visibility")
- Describe what they did and why it matters — behaviors and decisions, not just deliverables
- Include one specific moment you personally observed if possible
Principles (your company's defined principles):
- Lead with first-hand evidence, supplement with brag sheet
- Each principle should have distinct evidence — don't repeat the same example
- Reference specific behaviors, not generic praise
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 103 lines · 0 tokens per session scan A 734d3eaa3dc2
om-review-peer is a command published in the GitHub repository breferrari/obsidian-mind (4,620 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,019 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
session-stop
Stop recording and save this agent session to the project ledger.
pdf-to-wiki
A workflow for sending a large PDF from Google Drive to NotebookLM, Google's document-analysis tool, and saving the resulting notes as Obsidian markdown files. It passes the file link rather than reading the PDF directly.
sol
Run a one-shot task on the routed Codex model (gpt-5.6-sol by default) and relay its answer.
setup
Configure Vault PKM plugin — set vault path, API keys, and verify setup.
setup-mcp-claude-code
Build and register the Contorium MCP server for Claude Code or Cursor Agent.
refresh-context
Re-snapshot Core Context.md from (optional) mothership system files + key personal essays. Run when mothership files change, when new essays signal philosophy shift, or when snapshot is older than 30 days.